https://wmdp-quality.pl/
WMDP
https://www.wmdp.ai/
WMDP Benchmark
Measuring and Reducing Malicious Use With Unlearning
benchmark
https://openreview.net/forum?id=xlr6AUDuJz&referrer=%5Bthe%20profile%20of%20Xiaoyuan%20Zhu%5D(%2Fprofile%3Fid%3D~Xiaoyuan_Zhu2)
The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning | OpenReview
The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing...
benchmarkmeasuring